[HBASE-18085] Prevent parallel purge in ObjectPool

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 2.0.0
• Hadoop Flags: Reviewed
• Assignee: Yu Li
• Reporter: Yu Li
• Created: 19/May/17 19:04
• Updated: 01/Aug/18 06:24
• Resolved: 24/May/17 07:57

Description

Parallel purge in ObjectPool is meaningless and will cause contention issue since ReferenceQueue#poll has synchronization (source code shown below)

    public Reference<? extends T> poll() {
        if (head == null)
            return null;
        synchronized (lock) {
            return reallyPoll();
        }
    }

We observed threads blocking on the purge method while using offheap bucket cache, and we could easily reproduce this by testing the 100% cache hit case in bucket cache with enough reading threads.

We propose to add a purgeLock and use tryLock to avoid parallel purge.